PROC GLM OR PROC MIX FOR BIOEQUIVALENCE STUDY

[superbibi]

Hi SAS Users,

I need to test bioequivalent between two treatment. Bioequivalence is defined as 90% CI of the geometric mean ratio between treatment and reference lines within 0.8 and 1.25. 

I have a sample data set that is from a guideline and I want to write the code which can generate the same outputs as the guideline. 

I used the ID,  seq, period, AUCt data in Table A1-E and A1-F from the linked PDF. It should come up with the output on Table A1-H and A1-I. 

https://www.canada.ca/content/dam/hc-sc/documents/services/drugs-health-products/drug-products/appli...

I also attached the sas data set here. 

I have tried several sets of code and cannot find the same outcome. Particularly the output on Table A1-I (parameter as subject(seq) and residual with their variance. How should I modify the code?

/* using proc mixed*/

PROC MIXED DATA = MBHC.SAMPLE;
CLASS ID SEQ PERIOD FORMULATION;
MODEL LNAUC =SEQ PERIOD FORMULATION/ DDFM = SATTERTH ;
RANDOM FORMULATION/TYPE = FA0(2) SUB = ID;
REPEATED/GRP = FORMULATION SUB = ID;
ESTIMATE "T VS. R" FORMULATION 1 -1/CL ALPHA = 0.1;
RUN;


/* using GLM*/

PROC GLM DATA=MBHC.SAMPLE ;

   CLASS ID SEQ PERIOD FORMULATION  ;
   MODEL LNAUC =SEQ PERIOD FORMULATION;

RUN ;

Output I want:

 Thank you.